Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense_h_to_4h",
+    "dense_4h_to_h",
     "dense",
-    "dense_4h_to_h"
+    "query_key_value",
+    "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809423ee5d1168c5341427049e0bdfe6f45466f8d4718dbb0f36d8ffc482e4d9
+oid sha256:a7c6933aa79e4ea4eab76da13aa1e10f7c9a85d135ea7fee1e5b4afb27c7ad8c
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b921ea871404c0ad6f1bc7595350aa61ee22a1daaf1d777d804b4dfc466f9a9
+oid sha256:7e39b3532c4ee383d1efd880a3c3876f03f245bf8a4078bb3116534b068d42eb
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8482585456f64ac9c5e34989d32f4ce51e3b9d3c750ed5faae1f674e6609b1ce
+oid sha256:271ef98c409fa090816d4b69e71ea6bba81b47215700ad081b4ecf5fd50f4a01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00016304569355561895,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0021195940162230466,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00016304569355561895,
       "eval_loss": 11.112594604492188,
-      "eval_runtime": 19.8094,
-      "eval_samples_per_second": 130.393,
-      "eval_steps_per_second": 65.222,
+      "eval_runtime": 19.5299,
+      "eval_samples_per_second": 132.259,
+      "eval_steps_per_second": 66.155,
       "step": 1
+    },
+    {
+      "epoch": 0.0008152284677780948,
+      "grad_norm": 0.808183491230011,
+      "learning_rate": 5e-05,
+      "loss": 44.4564,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "grad_norm": 0.7593473196029663,
+      "learning_rate": 0.0001,
+      "loss": 44.4328,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "eval_loss": 11.110093116760254,
+      "eval_runtime": 18.3475,
+      "eval_samples_per_second": 140.782,
+      "eval_steps_per_second": 70.418,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 16878403584.0,
+  "total_flos": 212185645056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d61215a44ad9f167200637bbe6f2333bca8d33cc85d7a09f40e2d2584aaf6a7
+oid sha256:537bedd261142e09291e40d33771f85f1d1b81152f9175802cccfe07fc78163e
 size 6776